Training in progress, step 3340, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cea960f50a7271a5b2bba71996a92c7510add6435cf258a5c6606f9afdf5a9f
+oid sha256:6cb99fa64546939c539783d29a25c42425044ee987ecc3e5696b8534c4e9f345
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d9cb9f3e787a8028fa8d1eca6622c7c4dfbba28974558a4fd13d01082cfc82
+oid sha256:cd641e98929b8b276a8de167087ef9ff9d89754bf78fd580019c0c5c609853d1
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:715afa7fa80b309ab5f3a3ffeab1c984abb1f23fc1fdeeb9a5d9e680a111f9d9
+oid sha256:8da95d53fc7692aea2c9104930a96fc9ba7cf5e6583572212fa22dac8a3dfc0b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba3845b027cbf32ba8978367629ed9d5fe41b951f8e9b22618a87d5fbc8d6666
+oid sha256:95230278efb9ecdcab5e159a83a7f79b4af787377ae2ff1f8e2e651daab268eb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2656,
+  "epoch": 0.2672,
   "eval_steps": 500,
-  "global_step": 3320,
+  "global_step": 3340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1169,6 +1169,13 @@
       "learning_rate": 2.856826595508678e-05,
       "loss": 3.6097,
       "step": 3320
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 42.991546630859375,
+      "learning_rate": 2.8547481435507382e-05,
+      "loss": 3.5292,
+      "step": 3340
     }
   ],
   "logging_steps": 20,
@@ -1176,7 +1183,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 7875682626207744.0,
+  "total_flos": 7927089491214336.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null